Milad-R's picture
First Push
bc020b7 verified
{
"name": "root",
"gauges": {
"SnowballTarget.Policy.Entropy.mean": {
"value": 1.0020674467086792,
"min": 1.0020674467086792,
"max": 2.8589038848876953,
"count": 20
},
"SnowballTarget.Policy.Entropy.sum": {
"value": 9567.740234375,
"min": 9567.740234375,
"max": 29278.03515625,
"count": 20
},
"SnowballTarget.Step.mean": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Step.sum": {
"value": 199984.0,
"min": 9952.0,
"max": 199984.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.mean": {
"value": 12.964086532592773,
"min": 0.3959653079509735,
"max": 12.99065113067627,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicValueEstimate.sum": {
"value": 2527.996826171875,
"min": 76.81726837158203,
"max": 2650.0927734375,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.mean": {
"value": 199.0,
"min": 199.0,
"max": 199.0,
"count": 20
},
"SnowballTarget.Environment.EpisodeLength.sum": {
"value": 8756.0,
"min": 8756.0,
"max": 10945.0,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.mean": {
"value": 0.06859463559650227,
"min": 0.06181348492348251,
"max": 0.07618042345982794,
"count": 20
},
"SnowballTarget.Losses.PolicyLoss.sum": {
"value": 0.27437854238600906,
"min": 0.24725393969393003,
"max": 0.3735940008231338,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.mean": {
"value": 0.20064456059652216,
"min": 0.11324607808480733,
"max": 0.2793227135404652,
"count": 20
},
"SnowballTarget.Losses.ValueLoss.sum": {
"value": 0.8025782423860887,
"min": 0.4529843123392293,
"max": 1.3746385252943227,
"count": 20
},
"SnowballTarget.Policy.LearningRate.mean": {
"value": 8.082097306000005e-06,
"min": 8.082097306000005e-06,
"max": 0.000291882002706,
"count": 20
},
"SnowballTarget.Policy.LearningRate.sum": {
"value": 3.232838922400002e-05,
"min": 3.232838922400002e-05,
"max": 0.00138516003828,
"count": 20
},
"SnowballTarget.Policy.Epsilon.mean": {
"value": 0.10269400000000001,
"min": 0.10269400000000001,
"max": 0.19729400000000002,
"count": 20
},
"SnowballTarget.Policy.Epsilon.sum": {
"value": 0.41077600000000003,
"min": 0.41077600000000003,
"max": 0.96172,
"count": 20
},
"SnowballTarget.Policy.Beta.mean": {
"value": 0.0001444306000000001,
"min": 0.0001444306000000001,
"max": 0.0048649706,
"count": 20
},
"SnowballTarget.Policy.Beta.sum": {
"value": 0.0005777224000000004,
"min": 0.0005777224000000004,
"max": 0.023089828,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.mean": {
"value": 25.477272727272727,
"min": 3.4318181818181817,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Environment.CumulativeReward.sum": {
"value": 1121.0,
"min": 151.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.mean": {
"value": 25.477272727272727,
"min": 3.4318181818181817,
"max": 25.581818181818182,
"count": 20
},
"SnowballTarget.Policy.ExtrinsicReward.sum": {
"value": 1121.0,
"min": 151.0,
"max": 1407.0,
"count": 20
},
"SnowballTarget.IsTraining.mean": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
},
"SnowballTarget.IsTraining.sum": {
"value": 1.0,
"min": 1.0,
"max": 1.0,
"count": 20
}
},
"metadata": {
"timer_format_version": "0.1.0",
"start_time_seconds": "1720461556",
"python_version": "3.10.12 (main, Nov 20 2023, 15:14:05) [GCC 11.4.0]",
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/SnowballTarget.yaml --env=./training-envs-executables/linux/SnowballTarget/SnowballTarget --run-id=SnowballTarget1 --no-graphics",
"mlagents_version": "1.1.0.dev0",
"mlagents_envs_version": "1.1.0.dev0",
"communication_protocol_version": "1.5.0",
"pytorch_version": "2.3.0+cu121",
"numpy_version": "1.23.5",
"end_time_seconds": "1720462011"
},
"total": 455.0014820000001,
"count": 1,
"self": 0.44411691600009817,
"children": {
"run_training.setup": {
"total": 0.057831999999962136,
"count": 1,
"self": 0.057831999999962136
},
"TrainerController.start_learning": {
"total": 454.49953308400006,
"count": 1,
"self": 0.5879936799823327,
"children": {
"TrainerController._reset_env": {
"total": 3.0645143980000285,
"count": 1,
"self": 3.0645143980000285
},
"TrainerController.advance": {
"total": 450.7544312130178,
"count": 18201,
"self": 0.27372523803740023,
"children": {
"env_step": {
"total": 450.4807059749804,
"count": 18201,
"self": 292.16906258698396,
"children": {
"SubprocessEnvManager._take_step": {
"total": 158.03027386900726,
"count": 18201,
"self": 1.4677043069931415,
"children": {
"TorchPolicy.evaluate": {
"total": 156.56256956201412,
"count": 18201,
"self": 156.56256956201412
}
}
},
"workers": {
"total": 0.2813695189892087,
"count": 18201,
"self": 0.0,
"children": {
"worker_root": {
"total": 453.29561899100304,
"count": 18201,
"is_parallel": true,
"self": 229.70966405001388,
"children": {
"run_training.setup": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"steps_from_proto": {
"total": 0.007852296000010028,
"count": 1,
"is_parallel": true,
"self": 0.006238952000103382,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0016133439999066468,
"count": 10,
"is_parallel": true,
"self": 0.0016133439999066468
}
}
},
"UnityEnvironment.step": {
"total": 0.06681781999998293,
"count": 1,
"is_parallel": true,
"self": 0.000708327999973335,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 0.0004137219999620356,
"count": 1,
"is_parallel": true,
"self": 0.0004137219999620356
},
"communicator.exchange": {
"total": 0.06375477599999613,
"count": 1,
"is_parallel": true,
"self": 0.06375477599999613
},
"steps_from_proto": {
"total": 0.0019409940000514325,
"count": 1,
"is_parallel": true,
"self": 0.0004029270002092744,
"children": {
"_process_rank_one_or_two_observation": {
"total": 0.0015380669998421581,
"count": 10,
"is_parallel": true,
"self": 0.0015380669998421581
}
}
}
}
}
}
},
"UnityEnvironment.step": {
"total": 223.58595494098915,
"count": 18200,
"is_parallel": true,
"self": 10.24604082095334,
"children": {
"UnityEnvironment._generate_step_input": {
"total": 5.292314342009377,
"count": 18200,
"is_parallel": true,
"self": 5.292314342009377
},
"communicator.exchange": {
"total": 174.81596824201551,
"count": 18200,
"is_parallel": true,
"self": 174.81596824201551
},
"steps_from_proto": {
"total": 33.23163153601092,
"count": 18200,
"is_parallel": true,
"self": 6.254605740988723,
"children": {
"_process_rank_one_or_two_observation": {
"total": 26.9770257950222,
"count": 182000,
"is_parallel": true,
"self": 26.9770257950222
}
}
}
}
}
}
}
}
}
}
}
}
},
"trainer_threads": {
"total": 0.00016415100003541738,
"count": 1,
"self": 0.00016415100003541738,
"children": {
"thread_root": {
"total": 0.0,
"count": 0,
"is_parallel": true,
"self": 0.0,
"children": {
"trainer_advance": {
"total": 445.21802090595213,
"count": 682824,
"is_parallel": true,
"self": 14.382400967046237,
"children": {
"process_trajectory": {
"total": 245.8147513779062,
"count": 682824,
"is_parallel": true,
"self": 245.14979968890646,
"children": {
"RLTrainer._checkpoint": {
"total": 0.6649516889997358,
"count": 4,
"is_parallel": true,
"self": 0.6649516889997358
}
}
},
"_update_policy": {
"total": 185.0208685609997,
"count": 90,
"is_parallel": true,
"self": 57.5771192860027,
"children": {
"TorchPPOOptimizer.update": {
"total": 127.443749274997,
"count": 4587,
"is_parallel": true,
"self": 127.443749274997
}
}
}
}
}
}
}
}
},
"TrainerController._save_models": {
"total": 0.09242964199984272,
"count": 1,
"self": 0.0009173429998554639,
"children": {
"RLTrainer._checkpoint": {
"total": 0.09151229899998725,
"count": 1,
"self": 0.09151229899998725
}
}
}
}
}
}
}